Skip to main content

Resultados relacionados

Resultados totales (Incluyendo duplicados): 9
Encontrada(s) 1 página(s)

e-Archivo. Repositorio Institucional de la Universidad Carlos III de Madrid
Publication Contribución de congreso (ConferenceOutput)

Demo: vrAIn proof-of-concept: a deep learning approach for virtualized RAN resource control

  • Ayala Romero, José A.
  • García Saavedra, Andrés
  • Gramaglia, Marco
  • Costa-Pérez, Xavier
  • Banchs Roca, Albert
  • Alcaraz, Juan J.
Proceeding of: 25th Annual International Conference on Mobile Computing and Networking (MobiCom'19), October 21-25, 2019, Los Cabos, Mexico., While the application of the NFV paradigm into the network is proceeding full steam ahead, there is still one last milestone to be achieved in this context: the virtualization of the radio access network (vRAN). Due to the very complex dependency between the radio conditions and the computing resources needed to provide the baseband processing functionality, attaining an efficient resource control is particularly challenging. In this demonstration, we will showcase vrAIn, a vRAN dynamic resource controller that employs deep reinforcement learning to perform resource assignment decisions. vrAIn, which is implemented using an open-source LTE stack over a Linux platform, can achieve substantial savings in the used CPU resources while maintaining the target QoS for the attached terminals and maximizing throughput when there is a deficit of computational capacity., The work of University Carlos III of Madrid was supported by H2020 5G-MoNArch project (grant agreement no. 761445) and H2020 5G-TOURS project (grant agreement no. 856950). The work of NEC Laboratories Europe was supported by H2020 5G-TRANSFORMER project (grant agreement no. 761536) and 5GROWTH project (grant agreement no. 856709). The work of University of Cartagena was supported by Grant AEI/FEDER TEC2016-76465-C2-1-R (AIM) and Grant FPU14/03701.
e-Archivo. Repositorio Institucional de la Universidad Carlos III de Madrid
Publication Contribución de congreso (ConferenceOutput)

Trading accuracy for privacy in machine learning tasks: an empirical analysis

  • Prodomo, Vittorio
  • González Sánchez, Roberto
  • Gramaglia, Marco
Proceeding of: IEEE Conference on Communications and Network Security (CNS 2021), 4-6 Oct. 2021, Tempe, AZ, USA (Virtual conference), Different kinds of user-generated data are increasingly used to tailor and optimize, through Machine Learning, the operation of online services and infrastructures. This typically requires sharing data among different partners, often including private data of individuals or business confidential data. While this poses privacy issues, the current state-of-the-art solutions either impose strong assumptions on the usage scenario or drastically reduce the data quality. In this paper, we evaluate through a generic framework the trade-offs between the accuracy of Machine Learning tasks and the achieved privacy (measured as similarity) on the input data, discussing trends and ways forward., The work of University Carlos III of Madrid was supported by the H2020 5G-TOURS project (grant no. 856950).
e-Archivo. Repositorio Institucional de la Universidad Carlos III de Madrid
Publication Contribución de congreso (ConferenceOutput)

AZTEC: anticipatory capacity allocation for zero-touch network slicing

  • Bega, Dario
  • Gramaglia, Marco
  • Fiore, Marco
  • Banchs Roca, Albert
  • Costa-Pérez, Xavier
Proceeding of: IEEE INFOCOM 2020 - IEEE Conference on Computer Communications 6-9 July 2020 (Virtual Conference), The combination of network softwarization with network slicing enables the provisioning of very diverse services over the same network infrastructure. However, it also creates a complex environment where the orchestration of network resources cannot be guided by traditional, human-in-the-loop network management approaches. New solutions that perform these tasks automatically and in advance are needed, paving the way to zero-touch network slicing.In this paper, we propose AZTEC, a data-driven framework that effectively allocates capacity to individual slices by adopting an original multi-timescale forecasting model. Hinging on a combination of Deep Learning architectures and a traditional optimization algorithm, AZTEC anticipates resource assignments that minimize the comprehensive management costs induced by resource overprovisioning, instantiation and reconfiguration, as well as by denied traffic demands.Experiments with real-world mobile data traffic show that AZTEC dynamically adapts to traffic fluctuations, and largely outperforms state-of-the-art solutions for network resource orchestration., The work of University Carlos III of Madrid was supported by H2020 5G-TOURS project (grant agreement no. 856950). The work of NEC Laboratories Europe was supported by H2020 5GROWTH project (grant agreement no. 856709). The research of M. Fiore was partially supported by ANR CANCAN project (ANR-18-CE25-0011).
e-Archivo. Repositorio Institucional de la Universidad Carlos III de Madrid
Publication Contribución de congreso (ConferenceOutput)

The touristic sector in the 5G technology era: the 5G-TOURS project approach

  • Vignaroli, Luca
  • Gramaglia, Marco
  • Fuentes, Manuel
  • Casella, Antonino
  • Odarchenko, Roman
  • Natale, Lorenzo
  • Altman, Baruch
  • D'Andria, Francesco
5G mobile networks are designed to fulfill very stringent requirements and support new vertical use cases. This transition to a vertical oriented delivery model will have a strong impact in the touristic sector. In this context, the "touristic city node" of 5G-TOURS, built in the city of Turin, aims at exploiting the potential of the media vertical. The objective is to develop an innovative tourism concept based on complementary and linked trials for five specific use cases. The trials will promote an overall integrated indoor/outdoor immersive experience to the visitors using any possible device, enhancing the accessibility to the technology especially for disadvantaged and disabled people. They will also utilize 5G to drive "remote tourism" based on AR/VR experiences and bridge the gap between the physical and virtual worlds for tourism. This paper provides an overview of the 5G technology deployed in the touristic node, explaining the different services to be provided and discussing the need of 5G technology to support this vision. This work also assesses the business potential of each of the considered use cases, corroborating their potential in the context of future network services., This work was supported in part by the European Commission under the 5G-TOURS: SmarT mObility, media and e-health for toURists and citizenS (H2020-ICT-2018-2020 call, grant number 856950).
e-Archivo. Repositorio Institucional de la Universidad Carlos III de Madrid
Publication Contribución de congreso (ConferenceOutput)

vrAIn: a deep learning approach tailoring computing and radio resources in virtualized RANs

  • Ayala Romero, José A.
  • García Saavedra, Andrés
  • Gramaglia, Marco
  • Costa-Pérez, Xavier
  • Banchs Roca, Albert
  • Alcaraz, Juan J.
Proceeding of: 25th Annual International Conference on Mobile Computing and Networking (MobiCom'19), October 21-25, 2019, Los Cabos, Mexico., The virtualization of radio access networks (vRAN) is the last milestone in the NFV revolution. However, the complex dependencies between computing and radio resources make vRAN resource control particularly daunting. We present vrAIn, a dynamic resource controller for vRANs based on deep reinforcement learning. First, we use an autoencoder to project high-dimensional context data (traffic and signal quality patterns) into a latent representation. Then, we use a deep deterministic policy gradient (DDPG) algorithm based on an actor-critic neural network structure and a classifier to map (encoded) contexts into resource control decisions. We have implemented vrAIn using an open-source LTE stack over different platforms. Our results show that vrAIn successfully derives appropriate compute and radio control actions irrespective of the platform and context: (i) it provides savings in computational capacity of up to 30% over CPU-unaware methods; (ii) it improves the probability of meeting QoS targets by 25% over static allocation policies using similar CPU resources in average; (iii) upon CPU capacity shortage, it improves throughput performance by 25% over state-of-the-art schemes; and (iv) it performs close to optimal policies resulting from an offline oracle. To the best of our knowledge, this is the first work that thoroughly studies the computational behavior of vRANs, and the first approach to a model-free solution that does not need to assume any particular vRAN platform or system conditions., The work of University Carlos III of Madrid was supported by H2020 5GMoNArch project (grant agreement no. 761445) and H2020 5G-TOURS project (grant agreement no. 856950). The work of NEC Laboratories Europe was supported by H2020 5GTRANSFORMER project (grant agreement no. 761536) and 5GROWTH project (grant agreement no. 856709). The work of University of Cartagena was supported by Grant AEI/FEDER TEC2016-76465-C2-1-R (AIM) and Grant FPU14/03701., Publicado
e-Archivo. Repositorio Institucional de la Universidad Carlos III de Madrid
Publication Contribución de congreso (ConferenceOutput)

Constrained network slicing games: achieving service guarantees and network efficiency

  • Zheng, Jiaxiao
  • De Veciana, Gustavo
  • Banchs Roca, Albert
Proceeding of: 18th International Symposium on Modeling and Optimization in Mobile, Ad Hoc and Wireless Networks (WiOpt 2020), Network slicing is a key capability for next generation mobile networks. It enables one to cost effectively customize logical networks over a shared infrastructure. A critical component of network slicing is resource allocation, which needs to ensure that slices receive the resources needed to support their services while optimizing network efficiency. In this paper, we propose a novel approach to slice-based resource allocation named Guaranteed seRvice Efficient nETwork slicing (GREET). The underlying concept is to set up a constrained resource allocation game, where (i) slices unilaterally optimize their allocations to best meet their (dynamic) customer loads, while (ii) constraints are imposed to guarantee that, if they wish so, slices receive a pre-agreed share of the network resources. The resulting game is a variation of the well-known Fisher market, where slices are provided a budget to contend for network resources (as in a traditional Fisher market), but (unlike a Fisher market) prices are constrained for some resources to provide the desired guarantees. In this way, GREET combines the advantages of a share-based approach (high efficiency by flexible sharing) and reservation-based ones (which provide guarantees by assigning a fixed amount of resources). We characterize the Nash equilibrium, best response dynamics, and propose a practical slice strategy with provable convergence properties. Extensive simulations exhibit substantial improvements over network slicing state-of-the-art benchmarks., The work of J. Zheng and G. de Veciana were supported in part by NSF CNS-1731658 and an Army Futures Command Grant W911NF1920333. The work of A. Banchs was funded in part by the Spanish Ministry of Education, Culture, and Sports with a Salvador de Madariaga grant together with the H2020 5G-TOURS European project (Grant Agreement No. 856950).
e-Archivo. Repositorio Institucional de la Universidad Carlos III de Madrid
Publication Contribución de congreso (ConferenceOutput)

Identifying common periodicities in mobile service demands with spectral analysis

  • Márquez Colás, María Cristina
  • Gramaglia, Marco
  • Fiore, Marco
  • Banchs Roca, Albert
  • Smoreda, Zbigniew
Proceeding of: 2020 Mediterranean Communication and Computer Networking Conference (MedComNet), Aroa, Italy, 17-19 June 2020, In this paper, we investigate the existence and prevalence of comparable dynamics in the temporal fluctuations for the traffic demands generated by mobile applications.To this end, we hinge upon a spectral analysis framework, by computing Discrete Fourier Transforms of the typical demands for tens of popular mobile services observed in an operational metropolitan-scale network. We filter, cluster, and analyse hundreds of frequency components, and identify a substantial set of regular patterns that are common across most service demands. We also unveil how several mobile services defy classification, and have instead highly distinguishing temporal dynamics., The work of Orange Labs was supported by ANR through the CANCAN project (ANR-18-CE25-0011). The work of UC3M was supported by the H2020 5G-TOURS project (grant agreement no. 856950).
e-Archivo. Repositorio Institucional de la Universidad Carlos III de Madrid
Publication Contribución de congreso (ConferenceOutput)

Experimenting with SRv6: a tunneling protocol supporting network slicing in 5G and beyond

  • Gramaglia, Marco
  • Sciancalepore, Vincenzo
  • Pérez, Ramón
  • Fernandez-Maestro, Francisco Javier
  • Serrano Yáñez-Mingot, Pablo
  • Banchs Roca, Albert
Proceeding of: IEEE 25th International Workshop on Computer Aided Modeling and Design of Communication Links and Networks (2020 CAMAD), 14-16 sept. 2020 (Virtual conference), With network slicing, operators can acquire and manage virtual instances of a mobile network, tailored to a given service, in this way maximizing flexibility whileincreasing the overall resource utilization. However, the currently used tunnelling protocol, i.e., GTP, might not be the most appropriate choice for the envisioned scenarios, given its unawareness of the underlay network. In this paper, we analyse the use of an alternative tunnelling protocol to transport user data, namely, Segment Routing IPv6 (SRv6). More specifically, we discuss its qualitative advantages, present a prototype implementation, and carry out an experimental comparison vs. GTP, confirming that it constitutes a valid alternative as tunnelling protocol, This work has been supported by the European Commission and the 5G-PPP H2020 Programme under the grants 825012 (5G-CARMEN), 815074 (5G-EVE) and 856950 (5GTOURS).
e-Archivo. Repositorio Institucional de la Universidad Carlos III de Madrid
Publication Contribución de congreso (ConferenceOutput)

The case for serverless mobile networking

  • Gramaglia, Marco
  • Serrano Yáñez-Mingot, Pablo
  • Banchs Roca, Albert
  • García Avilés, Ginés
  • García-Saavedra, Andrés
  • Pérez, Ramón
Proceeding of: IFIP Networking Conference 2020, Paris, France, 22-26 June 2020 (Virtual conference)., The softwarization of communication networks provides notable benefits, such as flexibility, improved resource efficiency, and commoditization. In exchange, softwarization requires an increased management overhead and the need to re-design network operation. While the mobile networking eco-system is currently adapting this new paradigm with other network-related aspects (e.g., network slicing), cloud computing already addressed such problems with the introduction of serverless architectures, also known as Function as a Service (FaaS). With this approach, the software is decomposed into its minimum building blocks, i.e., functions, maximizing scalability, resource efficiency, and flexibility. In this paper, we analyze the potential adoption of the FaaS paradigm by the mobile networking ecosystem, discussing the implicit advantages, the challenges to address, and some solutions to overcome them., This work was partially supported by the European Commission in the framework of the H2020 5G-PPP 5G-EVE 5GROWTH, and 5G-TOURS projects.